CrewAI Server-Side Request Forgery Vulnerability
Vulnerability
A server-side request forgery (SSRF) vulnerability has been identified in CrewAI, a tool for building and managing multi-agent AI systems. This vulnerability allows attackers to access content from internal and cloud services. The issue arises because the RAG search tools in CrewAI do not properly validate URLs provided at runtime. The vulnerability is present in CrewAI versions with the Code Interpreter Tool enabled, either by default or through manual addition by the developer.
Impact
Exploitation of this vulnerability allows for unauthorized access to internal and cloud services, potentially leading to further exploitation of the system or application.
Remediation
Users are advised to remove or restrict the Code Interpreter Tool wherever possible, avoid enabling the 'allow_code_execution' setting unless necessary, and monitor Docker availability to prevent fallback to insecure sandbox modes.
Vulnerability Rating
Our algorithm analyzes dozens of metrics to generate these 8 key vulnerability categories, which are then combined to calculate the overall risk score.
